Color cast detection and correction method and device based on HSV (Hue, Saturation, Value) color space

Abstract

The invention provides a color cast detection and correction method and device, relating to the technical field of digital image processing. The method comprises the following steps of: inputting an image to be detected of an RGB (Red, Green, Blue) color space; calculating an S channel in the HSV (Hue, Saturation, Value) color space; counting the histogram vector h of the S channel; quantizing and filtering the histogram vector h; judging whether color cast exists in the image according to a histogram vector h' obtained after the quantizing and the filtering; if the image is judged to has color cast, respectively counting the contribution rates of an RGB channel to the maximum matrix and the minimum matrix, and judging a color cast channel according to the contribution rates; adjusting the value of the color cast channel in the RGB color space, recalculating the value of the S channel and judging whether color cast exists in the S channel, and repeating to execute until no color cast exists; and if the image is judged to have no color cast, ending the program. By using the color cast detection and correction method and device, various types of color cast images can be effectively detected and corrected, and the defects in the traditional method are overcome; and the color cast detection and correction method and device are favorable in adaptability to different scenes and high in algorithm efficiency.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to the use of algorithms such as color space conversion, histogram statistics, and median filtering in color cast detection and correction. Background technique [0002] Color is one of the important characteristics of images, and it is also an important basis for image processing and analysis. In a physical sense, the color of an object observed by the human eye is not only determined by its reflective properties, but also by the color of the light that hits the object. The human visual system has color constancy, which can eliminate the influence of lighting conditions and other factors on color to a certain extent, and correctly perceive the color of objects. However, imaging equipment does not have this "adjustment" function, and there is often a certain degree of error between the image it collects and the real color of the object surface, that is, color c...

AI Technical Summary

Problems solved by technology

However, the detection of white points often lacks versatility, and it does not perform well when there is no specular surface in the image or the image brightness is low.

However, the current classical algorithms all have certain deficiencies. For example, for images with monotonous colors or images containing large areas of color patches, the gray world algorithm often has the problem of correction failure, and sometimes over-correction occurs; when the image does not exist When the mirror surface or image brightness is low, the perfect reflection algorithm often performs poorly; when the image has a large range of colored textures, the edge-based white balance algorithm often fails; and for the fuzzy neural network algorithm, a lot of prior learning is required. Knowledge, and there are problems such as high consumption of logic units and high power consumption

Images